← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-oQ5

M1 Max (32c) · 32 GB · 5bit · 2026-05-22
Performance
16k
tokens
737.8
PP tok/s
38.0
TG tok/s
22207
TTFT (ms)
18.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 644.3 45.0 17.4 GB view
4k 732.1 43.0 18.1 GB view
8k 766.6 41.6 18.2 GB view
16k 737.8 38.0 18.7 GB current
32k 670.1 32.2 19.6 GB view
64k 530.3 21.1 21.6 GB view